Brett Goldstein

Picking Good Startup Ideas in the Vibe Coding Era

Founder/CEO of Micro and early-stage investor focused on AI-era products.

Students learn a clear process to assess ideas and decide which are worth pursuing.

Framework for Evaluating Startup Ideas

Students understand what investors look for and how to judge whether an idea has real funding potential.

How to Tell if an Idea Is Venture-Backable

Students learn how to evaluate if an idea can maintain an edge as AI speeds up building and copying.

Assessing Defensibility in the AI Era

No matter your background or experience, anyone can create apps. This course helps you avoid common pitfalls.

AI Product Manager and Instructor

Citi

Adobe

Atlassian

American Airlines

Bank of America

Drew Falkman

Startup advisor and product strategist has worked with HP, Adobe and many more.

Cohort 3

Cohort 4

No-code tools allow virtually anyone to build apps like having your own dev team. While you don't have to know any programming languages, there are a lot of potential false steps you can make when you are first learning to use these tools.In this course, we will introduce you to "vibe coding" the right way. Specifically, you will learn:🔥 How to plan your product before you start using the Vibe PRD that will be embedded in every prompt to ensure that your product has a clear vision and the vibe coder doesn't hallucinate or make incorrect assumptions.🔥 How to optimize Lovable to build a solid app quickly.🔥 How and why to create a database to store user and other data.🔥 How to manage your data effectively and securely using Supabase, including a SQL primer.🔥 How to AI-enable your vibe coded apps using ChatGPT, Claude or other LLMs.🔥 How to integrate other tools to make highly interactive UIs, integrate payments with Stripe, integrate email functionality and more.🔥 How to integrate with a larger team by exporting code to GitHub.🔥 How to deploy your apps to production.After just 4 weeks, you will be a master vibe coder with your own fully-featured and working application live!

Learn how to build your application using AI no-code tools in just 4 weeks.

Learn how to build great apps using Lovable

Build and integrate a database backend

Integrate ChatGPT, Claude and other APIs (like Stripe) and Javascript libraries

Build your own app

Learn vibe coding best practices

Product managers who want to take their ideas to an app to test a problem space, or to not be beholden to their dev team's fat backlog,

UX designers who want to be able to take their design ideas directly to a live application to validate or just ship.

Non-technical founders who have a great idea but need to build an app without having to hire a developer.

Build 🏗️, ship 🚢, and share 🚀 an end-to-end LLM application with AI-assisted development, vibe-coding, vibe-checking, and leading tools.

AIEO2

Co-Founder & CEO @ AI Makerspace

AI Makerspace

FourthBrain

University of Dayton

"Dr. Greg" Loughnane, Ph.D.

Co-Founder & CEO @ AI Makerspace | #unautomatable | TEDx Speaker

Data Scientist @ Fannie Mae

Fannie Mae

Transurban

Kat "KatGPT" Gawthorpe, Ph.D.

Co-Founder @ eve.ai | Econometrics @ Fannie Mae

AIEO1

AIEO3

Are you an aspiring AI Engineer?Even though you'll mostly work on the backend, the best AI Engineers can build end-to-end, shareable prototypes.That's what this course is all about.How should we:<ol><li>🎧 Vibe code a frontend</li><li>🚢 Build a scalable backend</li><li>🔀 Connect the two ends</li><li>🚀 Deploy our application to a public endpoint</li></ol>The "shell" of E2E applications is important to understand, even though the backend is likely to be the bottleneck in production.What happens when you need to connect to large databases, use custom models, leverage large libraries or packages, do advanced retrieval to augment generations, or build multi-agent systems that have to manage context as well as short and long-term memory?This is where the AI Engineering comes in.This course prepares you for it by learning to build simple, end-to-end applications.TL; DR <a target="_blank" rel="noopener noreferrer nofollow" href="https://www.notion.so/The-AI-Engineering-Onramp-Cohort-1-Course-Schedule-Curriculum-v0-23-299cd547af3d80c381fcdccff43da500">full curriculum details</a>Why we built this courseAfter working with &gt;400 students since January 2024 in <a target="_blank" rel="noopener noreferrer nofollow" href="https://maven.com/aimakerspace/ai-eng-bootcamp">The AI Engineering Bootcamp</a>, we've seen many who were unable to shareable, end-to-end prototypes even if they were capable of building very complex backends!

Build 🏗️, ship 🚢, and share 🚀 end-to-end LLM applications with Cursor

🧑‍💻 Set up a professional AI-Assisted Interactive Development Environment

🎧 Learn best (and worst) practices for Vibe Coding with Coding Agents

🚢 Build and deploy three end-to-end LLM applications

To make the most out of the course, you will want to set up your AI-assisted Interactive Development Development Environment before Day 1.

Preliminary understanding of Python, IDE's, CLI programming, and Git

Set up Google Colab, GitHub, OpenAI API key, Cursor, Docker, Render, and (Windows Only) WSL2 to make the most out of the first live session!

(Recommended) Tooling Setup!

Aspiring AI Engineers who do not yet code every day, but know they want to code every day.

Aspiring AI Engineering Leaders who lead coders and want skin in the game on building, evaluating, and deploying LLM applications.

Potential Aspiring AI Engineers who do not yet code every day, but think they might want to code every day.

Turn your idea into a working prototype in 7 days using AI & no-code tools. Learn, build, and launch—no tech skills required

15+ years Product&Marketing, 100+ MVPs 

Miro

LEGO®

Readymag

Microsoft

Elena Avramenko

15+ yrs in Product & Marketing, award-winning founder, 100+ new product launches

The first cohort and fastest path to success

Let's close this year Right! 

TL;DR:You don’t need a tech co-founder or coding skills to bring your idea to life.In just one week, you’ll learn how to validate, build, and test your startup MVP using the most powerful AI tools available today — no technical background required.There has never been a better time in history to become an entrepreneur.With the right guidance and AI-powered workflow, you can turn your idea into a real, working product faster than ever before.This fast-paced bootcamp gives you practical experience across the full startup cycle — from discovery and validation to MVP building and go-to-market testing — all powered by modern AI and no-code tools.You’ll walk away knowing which tools to use (and which to ignore), how to build a functional MVP, design a simple user journey, and test with real users — all without writing a single line of code.Accelerate your path to a working, testable prototype and save 3–6 months, equity, and money.🧭 What Makes This Course DifferentYou’re not watching tutorials — you’re building with expert guidance.Get live, hands-on support from Elena and join guest sessions on Go-to-Market, Design as a Differentiator, and Positioning Fundamentals.

The startup you always wanted to build? Time to make it real.

Shape and validate your idea

Build your MVP with modern no-code AI tools

Use AI for every step of creation

Test and learn like a real product team

Understand what makes a startup-ready product 

Idea-stage solo founders who have no technical background but want to finally bring their vision to life.

Professionals exploring side projects who want to validate an idea before going all-in or quitting their job.

Curious builders and creators who love experimenting with the newest AI and no-code tools to build something useful — or just for fun.

Acquire and develop a critical skill for product managers who are leading and contributing to AI products.

GenAI Product Builder @ Google, ex-Meta

Marily Nika, Ph.D AI/ML

Senior Data, ML and GenAI Scientist

SHI International

National Association of REALTORS

George Zoto

Senior NLP/AI Scientist

Product Manager AI&ML @ Google

Diego Granados

Sr. ML Product Manager,  ex-Meta

Stanford University

Mark Cramer

Sr. ML Product Manager @ Meta

December 2025

“Does it work?”... “Is it good enough?”... “Can we ship it?”...How do you answer these questions for AI products? You’re responsible for “running evals” but what does that mean?How do you choose the right metrics, interpret fuzzy results, and make a confident decision?This course gives you a framework to do just that.<ul><li>Map user value to evaluation (eval) objectives so your metrics aren’t abstract. Define success then translate it into measurable criteria.</li><li>Choose metrics you can actually maintain: capability, safety, UX friction, latency, cost and “does this reduce support tickets or increase activation.”</li><li>Set ship/no-ship thresholds you can defend to leadership.</li><li>Build lightweight workflows that work in real teams: human review where it matters, automation where it lasts, documentation that drives decisions.</li><li>Consider domain constraints (e.g., healthcare safety) and know what to avoid: silent failures, misleading proxy metrics and tests that don’t reflect production.</li><li>Tie everything to ROI: impact vs unit cost, eval coverage vs reliability, and the minimum viable monitoring you need post-launch.</li></ul>Experience AI evals through a case-based approach with a real AI product that we evaluate together.

Eliminate uncertainty in shipping AI features

Make confident ship or hold decisions for AI features

Translate user value into clear evaluation goals

Choose the right metrics for capability, safety, UX, and cost

Set defensible thresholds leadership will trust

Build lightweight evaluation workflows teams can maintain

Navigate domain constraints and avoid common failures

PMs leading AI features, growth, or platform initiatives

PMs who partner with ML teams and want to set evaluation standards

PMs who need to make clear “ship or hold” calls without doing the engineering